Feature weighting for data analysis via evolutionary simulation
This provides an analytically tractable and provably convergent weighting method for data analysis, addressing a specific need in multi-objective optimization.
The paper tackles the problem of assigning feature weights for data analysis in multi-objective problems by proposing an evolutionary simulation algorithm that evolves weights via a replicator dynamic. It proves global convergence to a unique interior equilibrium, ensuring non-degenerate limiting weights.
We analyze an algorithm for assigning weights prior to scalarization in discrete multi-objective problems arising from data analysis. The algorithm evolves the weights (the relevance of features) by a replicator-type dynamic on the standard simplex, with update indices computed from a normalized data matrix. We prove that the resulting sequence converges globally to a unique interior equilibrium, yielding non-degenerate limiting weights. The method, originally inspired by evolutionary game theory, differs from standard weighting schemes in that it is analytically tractable with provable convergence.